Cross-level inference
Author(s)
Bibliographic Information
Cross-level inference
University of Chicago Press, 1995
- : pbk
Available at 14 libraries
  Aomori
  Iwate
  Miyagi
  Akita
  Yamagata
  Fukushima
  Ibaraki
  Tochigi
  Gunma
  Saitama
  Chiba
  Tokyo
  Kanagawa
  Niigata
  Toyama
  Ishikawa
  Fukui
  Yamanashi
  Nagano
  Gifu
  Shizuoka
  Aichi
  Mie
  Shiga
  Kyoto
  Osaka
  Hyogo
  Nara
  Wakayama
  Tottori
  Shimane
  Okayama
  Hiroshima
  Yamaguchi
  Tokushima
  Kagawa
  Ehime
  Kochi
  Fukuoka
  Saga
  Nagasaki
  Kumamoto
  Oita
  Miyazaki
  Kagoshima
  Okinawa
  Korea
  China
  Thailand
  United Kingdom
  Germany
  Switzerland
  France
  Belgium
  Netherlands
  Sweden
  Norway
  United States of America
Note
Includes bibliographical references (p. 235-243) and index
Description and Table of Contents
- Volume
-
ISBN 9780226002194
Description
In the last few years, new disputes have erupted over the use of group averages from census areas or voting districts to draw inferences about individual social behaviour. Social scientists, policy analysts and historians often have little choice about using this kind of data, but statistical analysis of them is fraught with pitfalls. The recent debates have led to a new menu of choices for the applied researcher. This volume explains why older methods like ecological regression so often fail, and it examines the promising new techniques for cross-level inference. Experts in statistical analysis of aggregate data, Christopher H. Achen and W. Philips Shively, contend that cross-level inference makes unusually strong demands on substantive knowledge, so that no one method, such as Goodman's ecological regression, will fit all situations. Criticizing Goodman's model and some recent attempts to replace it, the authors argue for a range of alternate techniques, including extensions of cross-tabular, regression analysis and unobservable variable estimators.
Table of Contents
Preface 1: Cross-Level Inference 2: Ecological Regression and Its Extensions 3: Bias in Goodman Ecological Regression: Partisanship Models 4: Problems of Specification in Cross-Level Models 5: Relaxing the Goodman Assumptions: Improved Estimation Using a Subset ofthe Assumptions 6: Relaxing the Goodman Assumptions: Working with Underidentified Models 7: Models with Unobservable Variables: More Partisanship Models 8: Tabular Approaches: The Method of Bounds and the Method of Differences 9: Contextual Studies and Aggregation References Index
- Volume
-
: pbk ISBN 9780226002200
Description
In the last few years, new disputes have erupted over the use of group averages from census areas or voting districts to draw inferences about individual social behaviour. Social scientists, policy analysts and historians often have little choice about using this kind of data, but statistical analysis of them is fraught with pitfalls. The recent debates have led to a new menu of choices for the applied researcher. This volume explains why older methods like ecological regression so often fail, and it examines the promising new techniques for cross-level inference. Experts in statistical analysis of aggregate data, Christopher H. Achen and W. Phillips Shively, contend that cross-level inference makes unusually strong demands on substantive knowledge, so that no one method, such as Goodman's ecological regression, will fit all situations. Criticizing Goodman's model and some recent attempts to replace it, the authors argue for a range of alternate techniques, including extensions of cross-tabular, regression analysis and unobservable variable estimators.
by "Nielsen BookData"